Final Project

library(tidyverse)

Registered S3 methods overwritten by 'dbplyr':
  method         from
  print.tbl_lazy     
  print.tbl_sql      
-- Attaching packages ------------------------------------------------------------------------ tidyverse 1.3.1 --
v ggplot2 3.3.5     v purrr   0.3.4
v tibble  3.1.2     v dplyr   1.0.7
v tidyr   1.1.3     v stringr 1.4.0
v readr   1.4.0     v forcats 0.5.1
-- Conflicts --------------------------------------------------------------------------- tidyverse_conflicts() --
x dplyr::filter() masks stats::filter()
x dplyr::lag()    masks stats::lag()

library(tidyr)
library(dplyr)
library(readr)
library(ggplot2)

steam_data <- read.csv(url("https://raw.githubusercontent.com/CaptainBlast096/Intro-to-Data-Science---Final-Project/main/data/steam.csv?token=AURDUTN5EIYEUABRMPJSEM3BCSBK2"))
steam_data

colnames(steam_data)
nrow(steam_data)
glimpse(steam_data)

filter(steam_data, developer == "Valve")

Warning in for (i in seq_along(cenv$extra)) { :
  closing unused connection 3 (https://raw.githubusercontent.com/CaptainBlast096/Intro-to-Data-Science---Final-Project/main/data/steam.csv?token=AUYBUGFTVT4MWJCRESJF6LDBB4YYG)

steam_data %>%
  filter(str_detect(steamspy_tags, "FPS")) 

steam_data %>%
  select(developer, steamspy_tags)

FPS_Studios <- steam_data %>%
  select(developer, steamspy_tags)

FPS_Studios%>%
  group_by(developer) %>%
  summarise(total = n()) %>%
  arrange(desc(total))

FPS_STudio <- FPS_Studios %>%
  filter(str_detect(steamspy_tags, "FPS"))

Top_Five_Studio <- FPS_STudio %>%
  group_by(developer) %>%
  summarise(total = n()) %>%
  arrange(desc(total)) 

print(Top_Five_Studio)

Top_Studio <- data.frame(
  Developers = c("Valve", "Id Software", "NovaLogic", "Gearbox Software", "Epic Games Inc."),
  Amount_of_fps_games = c(19, 16, 8, 7, 5)
)

ggplot(Top_Studio, aes(x=Developers, y=Amount_of_fps_games )) +
  geom_col()

#Lines filter the amount of row in each genre
Action <- steam_data %>%  filter(str_detect(steamspy_tags, "Action"))
Action

nrow(Action)

[1] 10344

FPS <- steam_data %>%  filter(str_detect(steamspy_tags, "FPS"))
FPS

nrow(FPS)

[1] 405

Shooter <- steam_data %>%  filter(str_detect(steamspy_tags, "Shooter"))
Shooter

nrow(Shooter)

[1] 227

Sci_fi <- steam_data %>%  filter(str_detect(steamspy_tags, "Sci-fi"))
Sci_fi

nrow(Sci_fi) 

[1] 157

Puzzle <- steam_data %>%  filter(str_detect(steamspy_tags, "Puzzle"))
Puzzle

nrow(Puzzle)

[1] 1167

Indie <- steam_data %>%  filter(str_detect(steamspy_tags, "Indie"))
Indie

nrow(Indie)

[1] 16232

Strategy <- steam_data %>%  filter(str_detect(steamspy_tags, "Strategy"))
Strategy

nrow(Strategy)

[1] 4180

Racing <- steam_data %>%  filter(str_detect(steamspy_tags, "Racing"))
Racing

nrow(Racing)

[1] 765

RPG <- steam_data %>%  filter(str_detect(steamspy_tags, "RPG"))
RPG

nrow(RPG)

[1] 2863

Casual <- steam_data %>%  filter(str_detect(steamspy_tags, "Casual"))
Casual

nrow(Casual)

[1] 8205

Horror <- steam_data %>%  filter(str_detect(steamspy_tags, "Horror"))
Horror

nrow(Horror)

[1] 566

Simulation <- steam_data %>%  filter(str_detect(steamspy_tags, "Simulation"))
Simulation

nrow(Simulation)

[1] 3284

 #Genres
Top_Games <- data.frame (Genres = c("Action", "FPS", "Shooter", "Sci-fi", "Puzzle", "Indie", "Strategy", "Racing", "RPG", "Casual", "Horror", "Simulation"), Amount = c(10344,405,227,157,1167,16232,4180,765,2863,8205,566,3284))
#ggplot(Top_Games, aes(x = Genres, y = Amount_of_games)) + geom_col(fill = "black") 
ggplot(Top_Games, aes(x = Genres, y = Amount, fill = Genres,)) + geom_bar(stat = "identity", width = 0.5) + labs(title = "Number of games in each genre", x = "", y = "Amount (per game)") + coord_flip()